Flexible Background Subtraction with Self-Balanced Local Sensitivity

St-Charles, Pierre-Luc; Bilodeau, Guillaume-Alexandre; Bergevin, Robert

doi:10.1109/cvprw.2014.67

Cited by 97 publications

(69 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The bio-inspired motion segmentation module is running with no configurable parameters. For evaluation purposes, several alternatives were used as BS method: MOG2, refers to the masks outputted by MOG2, available in OpenCV, using default parameters; GMM [7], KNN [7], AMBER [11], CwisarDH [12], Spectral360 [13], SuBSENSE [14] and FTSG [15] refer to the computed masks made available in the CDnet site [9]. These masks were generated with the parameters adjusted to maximize overall performance.…”

Section: Methodsmentioning

confidence: 99%

Bio-inspired Boosting for Moving Objects Segmentation

Martins

Carvalho

Côrte-Real

et al. 2016

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Developing robust and universal methods for unsupervised segmentation of moving objects in video sequences has proved to be a hard and challenging task. State-of-the-art methods show good performance in a wide range of situations, but systematically fail when facing more challenging scenarios. Lately, a number of image processing modules inspired in biological models of the human visual system have been explored in different areas of application. This paper proposes a bio-inspired boosting method to address the problem of unsupervised segmentation of moving objects in video that shows the ability to overcome some of the limitations of widely used state-of-the-art methods. An exhaustive set of experiments was conducted and a detailed analysis of the results, using different metrics, revealed that this boosting is more significant when challenging scenarios are faced and state-of-the-art methods tend to fail.

show abstract

Section: Methodsmentioning

confidence: 99%

Bio-inspired Boosting for Moving Objects Segmentation

Martins

Carvalho

Côrte-Real

et al. 2016

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…This is mainly due to imperfect foreground/background segmentation errors and calibration errors. In simulations we produced perfect silhouettes as input for our algorithm whereas in this realworld example we took the output of the foreground/background segmentation method SUBSENSE [St-Charles et al, 2014]. This method performs among the best in the CDnet 2014 Change Detection benchmark [Wang et al, 2014], but still shows significant errors on the produced silhouettes.…”

Section: Real World Datamentioning

confidence: 99%

Shape-from-Silhouettes Algorithm with Built-in Occlusion Detection and Removal

Slembrouck

Cauwelaert

Veelaert

et al. 2015

Proceedings of the 10th International Conference on Computer Vision Theory and Applications

View full text Add to dashboard Cite

Abstract:Occlusion and inferior foreground/background segmentation still poses a big problem to 3D reconstruction from a set of images in a multi-camera system because it has a destructive nature on the reconstruction if one or more of the cameras do not see the object properly. We propose a method to obtain a 3D reconstruction which takes into account the possibility of occlusion by combining the information of all cameras in the multicamera setup. The proposed algorithm tries to find a consensus of geometrical predicates that most cameras can agree on. The results show a performance with an average error lower than 2cm on the centroid of a person in case of perfect input silhouettes. We also show that tracking results are significantly improved in a room with a lot of occlusion.

show abstract

“…Texture-based features, such as a local binary pattern [4], are often used to adapt to illumination changes. In addition, some features and background models are combined to enhance the robustness to background changes [5,6]. However, these heuristic approaches work well only for scenes containing background features designed by the researchers.…”

Section: Introductionmentioning

confidence: 99%

Analytics of Deep Neural Network-Based Background Subtraction

et al. 2018

View full text Add to dashboard Cite

Deep neural network-based (DNN-based) background subtraction has demonstrated excellent performance for moving object detection. The DNN-based background subtraction automatically learns the background features from training images and outperforms conventional background modeling based on handcraft features. However, previous works fail to detail why DNNs work well for change detection. This discussion helps to understand the potential of DNNs in background subtraction and to improve DNNs. In this paper, we observe feature maps in all layers of a DNN used in our investigation directly. The DNN provides feature maps with the same resolution as that of the input image. These feature maps help to analyze DNN behaviors because feature maps and the input image can be simultaneously compared. Furthermore, we analyzed important filters for the detection accuracy by removing specific filters from the trained DNN. From the experiments, we found that the DNN consists of subtraction operations in convolutional layers and thresholding operations in bias layers and scene-specific filters are generated to suppress false positives from dynamic backgrounds. In addition, we discuss the characteristics and issues of the DNN based on our observation.

show abstract

Flexible Background Subtraction with Self-Balanced Local Sensitivity

Cited by 97 publications

References 16 publications

Bio-inspired Boosting for Moving Objects Segmentation

Bio-inspired Boosting for Moving Objects Segmentation

Shape-from-Silhouettes Algorithm with Built-in Occlusion Detection and Removal

Analytics of Deep Neural Network-Based Background Subtraction

Contact Info

Product

Resources

About